Alternative methods in the development of pedotransfer functions for soil hydraulic characteristics

Soil hydraulic properties are needed in the modeling of water flow and solute movement in the vadose zone. Pedotransfer functions (PTFs) have received the attention of many researchers for indirect determination of hydraulic properties from basic soil properties as an alternative to direct measurement. The objective of this study was to compare the performance of cascade forward network (CFN), multiple-linear regression (MLR), and seemingly unrelated regression (SUR) methods using prediction capabilities of point and parametric PTFs developed by these methods. The point PTFs estimated field capacity (FC), permanent wilting point (PWP), available water capacity (AWC), and saturated hydraulic conductivity (Ks) and the parametric PTFs estimated the van Genuchten retention parameters. A total of 180 soil samples was extracted from the UNSODA database and divided into two groups as 135 for the development and 45 for the validation of the PTFs. The model performances were evaluated with three statistical tools: the maximum error (ME), the model efficiency (EF), and the D index (D) using the observed and predicted values of a given parameter. Despite the fact that the differences among the three methods in prediction accuracies of the point and parametric PTFs were not statistically significant (p > 0.05) except θ_r and α (p < 0.05) based on the ANOVA test, overall MLR and SUR were somewhat better than CFN in prediction of the point PTFs, whereas CFN performed better than the other two methods in prediction of the parametric PTFs. The F.F values of FC and θ_r for CFN, MLR, and SUR methods were 0.705. 0.805, 0.795 and 0.356, −0.290, −0.290, respectively, which refer to the best and worst predictions. Properties (Ks, θ_r, α) having some difficulty in prediction were better predicted by CFN and SUR methods, where these methods predict all hydraulic properties from basic soil properties simultaneously rather than individually as in MLR. This suggests that multivariate analysis using such functional relationships between hydraulic properties and basic soil properties can be utilized in developing more accurate point and parametric PTFs with less time and effort.     

青海三江源地区土壤容重转换函数的建立与比较

Bulk density (BD) is an important soil physical property and has significant effect on soil water conservation function. Indirect methods, which are called pedotransfer functions (PTFs), have replaced direct measurement and can acquire the missing data of BD during routine soil surveys. In this study, multiple linear regression (MLR) and artificial neuron network (ANN) methods were used to develop PTFs for predicting BD from soil organic carbon (OC), texture and depth in the Three-River Headwater region of Qinghai Province, China. The performances of the developed PTFs were compared with 14 published PTFs using four indexes, the mean error (ME), standard deviation error (SDE), root mean squared error (RMSE) and coefficient of determination (R²). Results showed that the performances of published PTFs developed using exponential regression were better than those developed using linear regression from OC. Alexander (1980)-B, Alexander (1980)-A and Manrique and Jones (1991)-B PTFs, which had good predictions, could be applied for the soils in the study area. The PTFs developed using MLR (MLR-PTFs) and ANN (ANN-PTFs) had better soil BD predictions than most of published PTFs. The ANN-PTFs had better performances than the MLR-PTFs and their performances could be improved when soil texture and depth were added as predictor variables. The idea of developing PTFs or predicting soil BD in the study area could provide reference for other areas and the results could lay foundation for the estimation of soil water retention and carbon pool.     

利用土壤传递函数估算土壤水力学特性研究进展

Characterization of soil hydraulic properties is important to environment management; however, it is well recognized that it is laborious, time-consuming and expensive to directly measure soil hydraulic properties. This paper reviews the development of pedotransfer functions (PTFs) used as an alternative tool to estimate soil hydraulic properties during the last two decades. Modern soil survey techniques like satellite imagery/remote sensing has been used in developing PTFs. Compared to mechanistic approaches, empirical relationships between physical properties and hydraulic properties have received wide preference for predicting soil hydraulic properties. Many PTFs based on different parametric functions can be found in the literature. A number of researchers have pursued a universal function that can describe water retention characteristics of all types of soils, but no single function can be termed generic though van Genuchten (VG) function has been the most widely adopted. Most of the reported parametric PTFs focus on estimation of VG parameters to obtain water retention curve (WRC). A number of physical, morphological and chemical properties have been used as predictor variables in PTFs. Conventionally, regression algorithms/techniques (statistical/neural regression) have been used for calibrating PTFs. However, there are reports of utilizing data mining techniques, e.g., pattern recognition and genetic algorithm. It is inferred that it is critical to refine the data used for calibration to improve the accuracy and reliability of the PTFs. Many statistical indices, including root mean square error (RMSE), index of agreement (d), maximum absolute error (ME), mean absolute error (MAE), coefficient of determination (r²) and correlation coefficient (r), have been used by different researchers to evaluate and validate PTFs. It is argued that being location specific, research interest in PTFs will continue till generic PTFs are developed and validated. In future studies, improved methods will be required to extract information from the existing database.     

沿海滩涂农田耕层土壤饱和导水率间接方法的评价

为筛选和构建适合苏北沿海滩涂围垦农田耕层土壤饱和水力传导率间接估算的土壤转换函数,在典型地块实测土壤饱和导水率和相关土壤基本性质的基础上,分析了11种根据基本土壤性质预测饱和导水率的转换函数方法的适用性,同时探讨了基于人工神经网络方法的土壤转换函数的预测效果。结果表明:滩涂围垦农田耕层土壤平均饱和导水率为10.04 cm/d,属低透水强度;在现有的土壤饱和导水率转换函数中,Vereecken函数是最适合滩涂围垦农区土壤、具有最佳预测精度的转换函数,其预测均方根误差为8.154,其次是Li、Campbell和Rawls函数;以砂粒、粘粒、容重和有机质作为输入因子,基于人工神经网络的土壤转换函数较Vereecken函数其预测均方根误差降至7.920,在输入因子中增加土壤盐分指标可进一步提高饱和导水率的预测精度,其预测均方根误差降为7.634。本文的研究结果显示利用人工神经网络方法建立的转换函数可有效提高滩涂盐渍农田土壤饱和导水率的预测精度。     

Estimating the bulk density in 0– 20 cm of tilled soils in China’s Loess Plateau using support vector machine modeling

ABSTRACT

Pedotransfer functions (PTFs), as an indirect forecasting method, offer an alternative for labor-intensive bulk density (BD) measurements. In order to improve the forecasting accuracies, support vector machine (SVM) method was first used to develop PTFs for predicting BD. Cross-validation and grid-search methods were used to automatically determine the SVM parameters in the forecasting process. Soil texture and organic matter content were selected as input variables based on results of predecessors, coupled with gray correlation theory. And additional properties were added as inputs for improving PTF's accuracy and reliability. The performance of the PTF established by SVM method was compared with artificial neural network (ANN) method and published PTFs using two indexes: root-mean-square error (RMSE) and coefficient of determination(R²). Results showed that the average RMSE of published PTFs was 0.1053, and the R² was 0.4558. The RMSE of ANN–PTF was 0.0638, and the R² was 0.7235. The RMSE of SVM–PTF was 0.0558, and the R² was 0.7658. Apparently, the SVM–PTF had better performance, followed by ANN–PTF. Additionally, performances could be improved when accumulated receiving water was added as predictor variable. Therefore, the first application of SVM data mining techniques in the prediction of soil BD was successful, improved the accuracy of predictions, and enhanced the function of soil PTFs. The idea of developing PTFs using SVM method for predicting soil BD in the study area could provide a reference for other areas.     

Soil water-retention prediction from pedotransfer functions for some Indian soils

This paper discusses the development of pedotransfer functions (PTFs) and uses a multiple nonlinear regression technique to validate point and parametric PTFs for the estimation of a water-retention curve from basic soil properties such as particle-size distribution, bulk density and organic matter content. One hundred soil samples were collected at different depths from different locations in the Pavanje river basin that lies within the southern coastal region of Karnataka, India. Prediction accuracies were evaluated using the coefficient of determination (R ²), root mean square error (RMSE) and mean error (ME) between measured and predicted values. Overall, both point and parametric methods predicted water contents at selected water potentials with considerable accuracy. However, prediction of the soil water-retention curve using PTFs by point estimation method was relatively more successful (best case R ² = 0.983) for the sampled soils. F-tests were also conducted for all cases. For one regression equation, the p-value was zero and for other equation, values were close to zero. Critical comparative analysis was carried out on the performances of the point and parametric methods. Use of the developed PTFs is suggested for the prediction of a water-retention curve for loamy sand and sandy loam soils in this area of the coastal region of southern India.     

Applicability of site-specific pedotransfer functions and rosetta model for the estimation of dynamic soil hydraulic properties under different vegetation covers

Background, Aims, and Scope  During the last decades, different methods have been developed to determine soil hydraulic properties in the field and laboratory. These methodologies are frequently time-consuming and/or expensive. An indirect method, named Pedotransfer Functions (PTFs), was developed to predict soil hydraulic properties using other easily measurable soil (physical and chemical) parameters. This work evaluates the use of the PTFs included in the Rosetta model (Schaap et al. 2001) and compares them with PTFs obtained specifically for soils under two different vegetation covers. Methods  Rosetta software includes two basic types of pedotransfer functions (Class PTF and Continuous PTF), allowing the estimation of van Genuchten water retention parameters using limited (textural classes only) or more extensive (texture, bulk density and one or two water retention measurements) input data. We obtained water retention curves from undisturbed samples using the ‘sand box’ method for potentials between saturation and 20 kPa, and the pressure membrane method for potentials between 100 and 1500 kPa. Physical properties of sampled soils were used as input variables for the Rosetta model and to determine site-specific PTFs. Results  The Rosetta model accurately predicts water content at field capacity, but clearly underestimates it at saturation. Poor agreement between observed and estimated values in terms of root mean square error were obtained for the Rosetta model in comparison with specific PTFs. Discrepancies between both methods are comparable to results obtained by other authors. Conclusions  Site-specific PTFs predicted the van Genuchten parameters better than Rosetta model. Pedotransfers functions have been a useful tool to solve the water retention capacity for soils located in the southern Pyrenees, where the fine particle size and organic matter content are higher. The Rosetta model showed good predictions for the curve parameters, even though the uncertainty of the data predicted was higher than for the site-specific PTFs. Recommendations and Perspectives  The Rosetta model accurately predicts the retention curve parameters when the use is related with wide soil types; nevertheless, if we want to obtain good predictors using a homogenous soil database, specific PTFs are required. ESS-Submission Editor: Prof. Zhihong Xu, PhD (zhihong.xu@griffith.edu.au)     

基于人工神经网络的数据处理和多目标群方法用土壤传递函数(PTFs)估算保水性

Pedotransfer functions(PTFs) have been developed to estimate soil water retention curves(SWRC) by various techniques.In this study PTFs were developed to estimate the parameters(θ s,θ r,α and λ) of the Brooks and Corey model from a data set of 148 samples.Particle and aggregate size distribution fractal parameters(PSDFPs and ASDFPs,respectively) were computed from three fractal models for either particle or aggregate size distribution.The most effective model in each group was determined by sensitivity analysis.Along with the other variables,the selected fractal parameters were employed to estimate SWRC using multi-objective group method of data handling(mGMDH) and different topologies of artificial neural networks(ANNs).The architecture of ANNs for parametric PTFs was different regarding the type of ANN,output layer transfer functions and the number of hidden neurons.Each parameter was estimated using four PTFs by the hierarchical entering of input variables in the PTFs.The inclusion of PSDFPs in the list of inputs improved the accuracy and reliability of parametric PTFs with the exception of θ s.The textural fraction variables in PTF1 for the estimation of α were replaced with PSDFPs in PTF3.The use of ASDFPs as inputs significantly improved α estimates in the model.This result highlights the importance of ASDFPs in developing parametric PTFs.The mGMDH technique performed significantly better than ANNs in most PTFs.     

Predicting Cationic Exchange Capacity in Calcareous Soils of East-Azerbaijan Province,Northwest Iran

The aim of this research is to study the efficiency of pedotransfer functions (PTFs) and artificial neural networks (ANNs) for cationic exchange capacity (CEC) prediction using readily available soil properties. Here, 417 soil samples were collected from the calcareous soils located in East-Azerbaijan province, northwest Iran and readily available soil properties, such as particle size distribution (PSD), organic matter (OM) and calcium carbonate equivalent (CCE), were measured. The entire 417 soil samples were divided into two groups, a training data set (83 soil samples) and test data set (334 soil samples). The performances of several published and derived PTFs and developed neural network algorithms using multilayer perceptron were compared, using a test data set. Results showed that, based on statistics of RMSE and R², PTFs and ANNs had a similar performance, and there was no significant difference in the accuracy of the model results. The result of the sensitivity analysis showed that the ANN models were very sensitive to the clay variable (due to the high variability of the clay). Finally, the models tested in this study could account for 85% of the variations in cationic exchange capacity (CEC) of soils in the studied area.

Abbreviations: ANN: arti?cial neural networks; MLP: multilayer perceptron; MLR: multiple linear regression; PTFs: Pedotransfer Functions; RBF: Radial Basis Function; MAE: mean absolute error; MSE: mean square error; CEC: cationic exchange capacity